Publication

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

European Conference on Computer Vision (ECCV)


Abstract

LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the de facto method is to project a 3D point cloud to get a 2D LiDAR image and use convolutions to process it. Despite the similarity between regular RGB and LiDAR images, we are the first to discover that the feature distribution of LiDAR images changes drastically at different image locations. Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image. As a result, the capacity of the network is under-utilized and the segmentation performance decreases. To fix this, we propose Spatially-Adaptive Convolution (SAC) to adopt different filters for different locations according to the input image. SAC can be computed efficiently since it can be implemented as a series of element-wise multiplications, im2col, and standard convolution. It is a general framework such that several previous methods can be seen as special cases of SAC. Using SAC, we build SqueezeSegV3 for LiDAR point-cloud segmentation and outperform all previous published methods by at least 2.0% mIoU on the SemanticKITTI benchmark. Code and pretrained model are available at https://github.com/chenfengxu714/SqueezeSegV3.

Related Publications

All Publications

ACM CHI Virtual Conference on Human Factors in Computing Systems (CHI) - May 8, 2021

Armstrong: An Empirical Examination of Pointing at Non-Dominant Arm-Anchored UIs in Virtual Reality

Zhen Li, Joannes Chan, Joshua Walton, Hrvoje Benko, Daniel Wigdor, Michael Glueck

CHI - May 8, 2021

Understanding, Detecting and Mitigating the Effects of Coactivations in Ten-Finger Mid-Air Typing in Virtual Reality

Conor R. Foy, John J. Dudley, Aakar Gupta, Hrvoje Benko, Per Ola Kristensson

CHI - May 8, 2021

StickyPie: A Gaze-Based, Scale-Invariant Marking Menu Optimized for AR/VR

Sunggeun Ahn, Stephanie Santosa, Mark Parent, Daniel Wigdor, Tovi Grossman, Marcello Giordano

SIGGRAPH - August 9, 2021

Deep Relightable Appearance Models for Animatable Faces

Sai Bi, Stephen Lombardi, Shunsuke Saito, Tomas Simon, Shih-En Wei, Kevyn Mcphail, Ravi Ramamoorthi, Yaser Sheikh, Jason Saragih

To help personalize content, tailor and measure ads, and provide a safer experience, we use cookies. By clicking or navigating the site, you agree to allow our collection of information on and off Facebook through cookies. Learn more, including about available controls: Cookies Policy